Elijah Kirschmann retweeted
YOLOv9 just released, and now it's compatible with 🤗 Transformers.js!
That's right... near real-time object detection running locally in your browser: no server required! 🤯 Try it out yourself! 👇
🔗 Demo: hf.co/spaces/Xenova/yolov9-w…
Elijah Kirschmann retweeted
Upscale-A-Video was just released and it's so good! 🤯
It's a temporal-consistent Diffusion Model for video Super-Resolution, and has some of the best results I've ever seen, look at how sharp those lines become!
More details below ⬇️⬇️
Elijah Kirschmann retweeted
Runway Gen-2 can now generate videos from a starting image.
And the results are incredible!
Here are the best 8 examples I’ve found (PLUS tutorial at the end):
Elijah Kirschmann retweeted
Google is in trouble.
I got early 'Alpha' access to GPT-4 with browsing and ran some tests.
Here are 8 crazy things I found:
Elijah Kirschmann retweeted
LERF: Language Embedded Radiance Fields
TL;DR: Grounding CLIP vectors volumetrically inside a NeRF allows flexible natural language queries in 3D
abs: arxiv.org/abs/2303.09553
project page: lerf.io/
Elijah Kirschmann retweeted
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
abs: arxiv.org/abs/2301.10241
project page: sarafridov.github.io/K-Plane…
Elijah Kirschmann retweeted
🪐 Introducing Galactica. A large language model for science.
Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more.
Explore and get weights: galactica.org
Elijah Kirschmann retweeted
Diffusion-2-Mesh experiments. Touchdesigner proof of concept, as an alternative to MiDaS or NeRF
Immersive latent space.
Overcoming challenges every day. Dream big.
Tools used:
deforum.github.io
derivative.ca
#aiart #vr #stablediffusion #touchdesigner #deforum
Elijah Kirschmann retweeted
Stable Diffusion VR
Real-time immersive latent space. 🔥
Small clips are sent from the engine to be diffused. Once ready, they're queued back into the projection.
Tools used:
deforum.github.io
derivative.ca
#aiart #vr #stablediffusionart #touchdesigner #deforum
Elijah Kirschmann retweeted
Over the 7 weeks since Stable Diffusion's release, we've seen many amazing open-source contributions from the community. A lot of them have come in the form of awesome Google Colab notebooks! 🔥
Here is a thread of 14 awesome notebooks we've seen from the community ↓
Elijah Kirschmann retweeted
I'm so excited to continue work on this project! ✨
Stable Diffusion VR + TouchDesigner =
Real-time immersive latent space. (interior demo)
Tools used:
deforum.github.io
derivative.ca
#aiart #vr #StableDiffusionArt #touchdesigner #deforum
Elijah Kirschmann retweeted
The first successful round trip of locally generated images in the @StableDiffusion @Photoshop plugin (colorized with Neural Filters, just for fun).
Elijah Kirschmann retweeted
World's first Outpainting for Photoshop! #photoshop #stablediffusion Thanks @parlance_zz and @hafriedlander for great work. More info about new plugin and server version with many cool new features tomorrow.
Elijah Kirschmann retweeted
Excited to announce our work on novel view synthesis with diffusion models! Our model can lift a single 2d image into 3d.
3d-diffusion.github.io
Joint work w/ @wchan212 @rmbrualla @hojonathanho @taiyasaki @mo_norouzi
Elijah Kirschmann retweeted
Been playing around with some movements within 3D after being inspired by @TomLikesRobots's post.
#stabledifusion #aiart #deforum #generativeart @deforum
Elijah Kirschmann retweeted
I'm opening up Lexica's search API for anybody to use.
Now anyone can integrate with a library of tens of millions of Stable Diffusion generated images, all licensed Creative Commons, entirely for free.
Lexica API Docs: lexica.art/docs
Elijah Kirschmann retweeted
Introducing stablediffusion-infinity: #outpainting with #stablediffusion on an infinite canvas.
Implemented with @huggingface's #diffusers and @martinRenou 's #ipycanvas in a Jupyter notebook.
Check the code here:
github.com/lkwq007/stabledif…
Also available in colab.




















